Front. Inform. Technol. Electron. Eng All Journals

Jul 2021, Volume 22 Issue 7

  • Select all
  • Review
    Areview of computer graphics approaches to urban modeling from a machine learning perspective
    Tian FENG, Feiyi FAN, Tomasz BEDNARZ

    Urban modeling facilitates the generation of virtual environments for various scenarios about cities. It requires expertise and consideration, and therefore consumes massive time and computation resources. Nevertheless, related tasks sometimes result in dissatisfaction or even failure. These challenges have received significant attention from researchers in the area of computer graphics. Meanwhile, the burgeoning development of artificial intelligence motivates people to exploit machine learning, and hence improves the conventional solutions. In this paper, we present a review of approaches to urban modeling in computer graphics using machine learning in the literature published between 2010 and 2019. This serves as an overview of the current state of research on urban modeling from a machine learning perspective.

  • Orginal Article
    Aself-supervised method for treatment recommendation in sepsis
    Sihan ZHU, Jian PU

    Sepsis treatment is a highly challenging effort to reduce mortality in hospital intensive care units since the treatment response may vary for each patient. Tailored treatment recommendations are desired to assist doctors in making decisions efficiently and accurately. In this work, we apply a self-supervised method based on reinforcement learning (RL) for treatment recommendation on individuals. An uncertainty evaluation method is proposed to separate patient samples into two domains according to their responses to treatments and the state value of the chosen policy. Examples of two domains are then reconstructed with an auxiliary transfer learning task. A distillation method of privilege learning is tied to a variational auto-encoder framework for the transfer learning task between the low- and high-quality domains. Combined with the self-supervised way for better state and action representations, we propose a deep RL method called high-risk uncertainty (HRU) control to provide flexibility on the trade-off between the effectiveness and accuracy of ambiguous samples and to reduce the expected mortality. Experiments on the large-scale publicly available real-world dataset MIMIC-III demonstrate that our model reduces the estimated mortality rate by up to 2.3% in total, and that the estimated mortality rate in the majority of cases is reduced to 9.5%.

  • Orginal Article
    Bio-inspired cryptosystem on the reciprocal domain: DNA strands mutate to secure health data*
    S. AASHIQ BANU, Rengarajan AMIRTHARAJAN

    Healthcare and telemedicine industries are relying on technology that is connected to the Internet. Digital health data are more prone to cyber attacks because of the treasure trove of personal data they possess. This necessitates protection of digital medical images and their secure transmission. In this paper, an encryption technique based on DNA mutated with Lorenz and Lüchaotic attractors is employed to generate high pseudo-random key streams. The proposed chaos-DNA cryptic system operates on the integer wavelet transform (IWT) domain and a bio-inspired crossover, mutation unit for enhancing the confusion and diffusion phase in an approximation coefficient. Finally, an XOR operation is performed with a quantised chaotic set from the developed combined attractors. The algorithm attains an average entropy of 7.9973, near-zero correlation with an NPCR of 99.642%, a UACI of 33.438%, and a keyspace of 10203. Further, the experimental analyses and NIST statistical test suite have been designed such that the proposed medical image encryption technique has the potency to withstand any statistical, differential, and brute force attacks.

  • Orginal Article
    Analyzing close relations between target artifacts for improving IR-based requirement traceability recovery
    Haijuan WANG, Guohua SHEN, Zhiqiu HUANG, Yaoshen YU, Kai CHEN

    Requirement traceability is an important and costly task that creates trace links from requirements to different software artifacts. These trace links can help engineers reduce the time and complexity of software maintenance. The information retrieval (IR) technique has been widely used in requirement traceability. It uses the textual similarity between software artifacts to create links. However, if two artifacts do not share or share only a small number of words, the performance of the IR can be very poor. Some methods have been developed to enhance the IR by considering relations between target artifacts, but they have been limited to code rather than to other types of target artifacts. To overcome this limitation, we propose an automatic method that combines the IR method with the close relations between target artifacts. Specifically, we leverage close relations between target artifacts rather than just text matching from requirements to target artifacts. Moreover, the method is not limited to the type of target artifacts when considering the relations between target artifacts. We conduct experiments on five public datasets and take account of trace links between requirements and different types of software artifacts. Results show that under the same recall, the precisions on the five datasets improve by 40%, 8%, 20%, 4%, and 6%, respectively, compared with the baseline method. The precision on the five datasets improves by an average of 15.6%, showing that our method outperforms the baseline method when working under the same conditions.

  • Orginal Article
    Discovering semantically related technical terms and web resources inQ&Adiscussions
    Junfang JIA, Valeriia TUMANIAN, Guoqiang LI

    A sheer number of techniques and web resources are available for software engineering practice and this number continues to grow. Discovering semantically similar or related technical terms and web resources offers the opportunity to design appealing services to facilitate information retrieval and information discovery. In this study, we extract technical terms and web resources from a community of question and answer (Q&A) discussions and propose an approach based on a neural language model to learn the semantic representations of technical terms and web resources in a joint low-dimensional vector space. Our approach maps technical terms and web resources to a semantic vector space based only on the surrounding technical terms and web resources of a technical term (or web resource) in a discussion thread, without the need for mining the text content of the discussion. We apply our approach to Stack Overflow data dump of March 2018. Through both quantitative and qualitative analyses in the clustering, search, and semantic reasoning tasks, we show that the learnt technical-term and web-resource vector representations can capture the semantic relatedness of technical terms and web resources, and they can be exploited to support various search and semantic reasoning tasks, by means of simple K-nearest neighbor search and simple algebraic operations on the learnt vector representations in the embedding space.

  • Orginal Article
    Adaptive tracking control of high-orderMIMO nonlinear systems with prescribed performance
    Xuerao WANG, Qingling WANG, Changyin SUN
    2021, 22(7): 986-1001. https://doi.org/10.1631/FITEE.2000145

    In this paper, an observer-based adaptive prescribed performance tracking control scheme is developed for a class of uncertain multi-input multi-output nonlinear systems with or without input saturation. A novel finite-time neural network disturbance observer is constructed to estimate the system uncertainties and external disturbances. To guarantee the prescribed performance, an error transformation is applied to transfer the time-varying constraints into a constant constraint. Then, by employing a barrier Lyapunov function and the backstepping technique, an observer-based tracking control strategy is presented. It is proven that using the proposed algorithm, all the closed-loop signals are bounded, and the tracking errors satisfy the predefined time-varying performance requirements. Finally, simulation results on a quadrotor system are given to illustrate the effectiveness of the proposed control scheme.

  • Orginal Article
    Motor speed estimation and failure detection of a smallUAVusing density ofmaxima∗
    Jefferson S. SOUZA, Moises C. BEZERRIL, Mateus A. SILVA, Frank C. VERAS, Abel LIMA-FILHO, Jorge Gabriel RAMOS, Alisson V. BRITO
    2021, 22(7): 1002-1009. https://doi.org/10.1631/FITEE.2000149

    This work presents the application of the technique named signal analysis based on chaos using density of maxima to analyze brushless direct current motors. It uses a correlation coefficient estimated from the density of maxima of the current signal. This study demonstrates in experiments the speed estimation of a brushless motor on a testbench and failure detection in a small flying drone. The experimental results demonstrate that it is possible to estimate the speed in 97.8% of the cases and to detect failure in 82.75% of the analyzed cases.

  • Orginal Article
    An improved Merkle hash tree based secure scheme for bionic underwater acoustic communication
    Masoud KAVEH, Abolfazl FALAHATI
    2021, 22(7): 1010-1019. https://doi.org/10.1631/FITEE.2000043

    Recently, bionic signals have been used to achieve covert underwater acoustic communication (UWAC) with high signal-to-noise ratios (SNRs) over transmission systems. A high SNR allows the attackers to proceed with their mischievous goals and makes transmission systems vulnerable against malicious attacks. In this paper we propose an improved Merkle hash tree based secure scheme that can resist current underwater attacks, i.e., replay attack, fabricated message attack, message-altering attack, and analyst attack. Security analysis is performed to prove that the proposed scheme can resist these types of attacks. Performance evaluations show that the proposed scheme can meet UWAC limitations due to its efficiency regarding energy consumption, communication overhead, and computation cost.

  • Orginal Article
    A data-driven method for estimating the target position of low-frequency sound sources in shallow seas
    Xianbin SUN, Xinming JIA, Yi ZHENG, Zhen WANG
    2021, 22(7): 1020-1030. https://doi.org/10.1631/FITEE.2000181

    Estimating the target position of low-frequency sound sources in a shallow sea environment is difficult due to the high cost of hydrophone placement and the complexity of the propagation model. We propose a compressed recurrent neural network (C-RNN) model that compresses the signal received by a vector hydrophone into a dynamic sound intensity signal and compresses the target position of the sound source into a GeoHash code. Two types of data are used to carry out prior training on the recurrent neural network, and the trained network is subsequently used to estimate the target position of the sound source. Compared with traditional mathematical models, the C-RNN model functions independently under the complex sound field environment and terrain conditions, and allows for real-time positioning of the sound source under low-parameter operating conditions. Experi-mental results show that the average error of the model is 56 m for estimating the target position of a low-frequency sound source in a shallow sea environment.